PERF(observability): reduce replicas, add priority

- Reduce Prometheus replicas from 2 to 1
- Reduce Grafana replicas from 2 to 1
- Reduce Blackbox-exporter replicas from 2 to 1
- Move Loki, Thanos, Tempo to workers (remove tolerations)
- Add medium-priority to Prometheus, Loki, Thanos, Tempo

blackbox-exporter/helm-values.yaml

@@ -3,7 +3,7 @@
 
 fullnameOverride: blackbox-exporter
 
-replicas: 2
+replicas: 1
 
 resources:
   requests:

grafana/helm-values.yaml

@@ -3,7 +3,7 @@
 
 fullnameOverride: grafana
 
-replicas: 2
+replicas: 1
 
 affinity:
   podAntiAffinity:

loki/helm-values.yaml

@@ -56,13 +56,8 @@ singleBinary:
   extraVolumeMounts:
     - name: data
       mountPath: /var/loki
-  # Run on master node for stability
+  # Medium priority for observability
-  tolerations:
+  priorityClassName: medium-priority
-    - key: node-role.kubernetes.io/control-plane
-      operator: Exists
-      effect: NoSchedule
-  nodeSelector:
-    node-role.kubernetes.io/control-plane: "true"
   resources:
     requests:
       cpu: 23m

prometheus/helm-values.yaml

@@ -70,10 +70,13 @@ prometheus:
     # Enable remote write receiver for OTel Collector
     enableRemoteWriteReceiver: true
 
-    # HA: 2 replicas on different worker nodes
+    # Single replica (HA removed for resource optimization)
-    replicas: 2
+    replicas: 1
     replicaExternalLabelName: prometheus_replica
 
+    # Medium priority for observability
+    priorityClassName: medium-priority
+
     # Pod anti-affinity for HA
     affinity:
       podAntiAffinity:

tempo/helm-values.yaml

@@ -7,13 +7,8 @@
 # - OTLP receiver for OpenTelemetry data
 # - Integrates with Grafana for trace visualization
 
-# Run on master node for stability
+# Medium priority for observability
-tolerations:
+priorityClassName: medium-priority
-  - key: node-role.kubernetes.io/control-plane
-    operator: Exists
-    effect: NoSchedule
-nodeSelector:
-  node-role.kubernetes.io/control-plane: "true"
 
 # =============================================================================
 # Resource Limits (optimized for small cluster)

thanos/helm-values.yaml

@@ -29,13 +29,8 @@ query:
   enabled: true
   replicaCount: 1
 
-  # Run on master node for stability
+  # Medium priority for observability
-  tolerations:
+  priorityClassName: medium-priority
-    - key: node-role.kubernetes.io/control-plane
-      operator: Exists
-      effect: NoSchedule
-  nodeSelector:
-    node-role.kubernetes.io/control-plane: "true"
 
   # Deduplicate metrics from multiple Prometheus replicas
   dnsDiscovery: